mirror of
https://github.com/denizsafak/abogen.git
synced 2026-07-18 05:40:26 +02:00
Artem Akymenko
1d7a2aeed6
- Extract safe_int, group_chunks_by_chapter, record_override_usage, chunk_text_for_tts - Add tests/test_chunk_utils.py (15 tests) - Update test_chunk_helpers.py and test_chunk_text_for_tts_prefers_raw.py imports - conversion_runner.py: 1574 → 1518 lines - All tests pass
26 lines
764 B
Python
26 lines
764 B
Python
from abogen.domain.chunk_utils import chunk_text_for_tts
|
|
|
|
|
|
def test_chunk_text_for_tts_prefers_text_over_normalized_text():
|
|
entry = {
|
|
# Simulate a pre-normalized chunk that lost the asterisk.
|
|
"normalized_text": "Unfuk",
|
|
# Raw chunk should preserve censored token for manual overrides.
|
|
"text": "Unfu*k",
|
|
}
|
|
|
|
assert chunk_text_for_tts(entry) == "Unfu*k"
|
|
|
|
|
|
def test_chunk_text_for_tts_falls_back_to_original_text_then_normalized_text():
|
|
entry = {
|
|
"original_text": "Hello * world",
|
|
"normalized_text": "Hello world",
|
|
}
|
|
assert chunk_text_for_tts(entry) == "Hello * world"
|
|
|
|
entry2 = {
|
|
"normalized_text": "Only normalized",
|
|
}
|
|
assert chunk_text_for_tts(entry2) == "Only normalized"
|